Update robots.txt
This commit is contained in:
parent
82eba1740e
commit
e338557f46
|
@ -1,7 +1,52 @@
|
|||
# Disallow crawling of specific directories and file types
|
||||
User-agent: *
|
||||
Disallow: /*.asc.txt$
|
||||
Disallow: /*.pdf$
|
||||
Disallow: /documents/
|
||||
Disallow: /img/
|
||||
|
||||
# https://github.com/ai-robots-txt/ai.robots.txt/
|
||||
User-agent: AI2Bot
|
||||
User-agent: Ai2Bot-Dolma
|
||||
User-agent: Amazonbot
|
||||
User-agent: anthropic-ai
|
||||
User-agent: Applebot
|
||||
User-agent: Applebot-Extended
|
||||
User-agent: Bytespider
|
||||
User-agent: CCBot
|
||||
User-agent: ChatGPT-User
|
||||
User-agent: Claude-Web
|
||||
User-agent: ClaudeBot
|
||||
User-agent: cohere-ai
|
||||
User-agent: Diffbot
|
||||
User-agent: DuckAssistBot
|
||||
User-agent: FacebookBot
|
||||
User-agent: facebookexternalhit
|
||||
User-agent: FriendlyCrawler
|
||||
User-agent: Google-Extended
|
||||
User-agent: GoogleOther
|
||||
User-agent: GoogleOther-Image
|
||||
User-agent: GoogleOther-Video
|
||||
User-agent: GPTBot
|
||||
User-agent: iaskspider/2.0
|
||||
User-agent: ICC-Crawler
|
||||
User-agent: ImagesiftBot
|
||||
User-agent: img2dataset
|
||||
User-agent: ISSCyberRiskCrawler
|
||||
User-agent: Kangaroo Bot
|
||||
User-agent: Meta-ExternalAgent
|
||||
User-agent: Meta-ExternalFetcher
|
||||
User-agent: OAI-SearchBot
|
||||
User-agent: omgili
|
||||
User-agent: omgilibot
|
||||
User-agent: PerplexityBot
|
||||
User-agent: PetalBot
|
||||
User-agent: Scrapy
|
||||
User-agent: Sidetrade indexer bot
|
||||
User-agent: Timpibot
|
||||
User-agent: VelenPublicWebCrawler
|
||||
User-agent: Webzio-Extended
|
||||
User-agent: YouBot
|
||||
Disallow: /
|
||||
|
||||
Sitemap: https://ethanyoo.com/sitemap.xml
|
||||
|
|
Loading…
Reference in New Issue